检索结果-内蒙古大学图书馆

IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

作者： Zhiyong Wang Zheru Chi Dagan Feng Center for Multimedia Signal Processing Department of Electronic and Information Engineering Hong Kong Polytechnic University Kowloon Hong Kong China

Generally, the more features utilized, the better the retrieval performance. However, it is a very challenging task to combine different feature sets in a way reflecting human perception. This paper presents the combination of different shape based feature sets using fuzzy integral for leaf image retrieval. The feature sets used in our system include centroid-contour distance curve, eccentricity, and angle code histogram. The fuzzy integral approach can release the user's burden from tuning the combination parameters. In order to reduce the matching time in the retrieval process, a thinning based method is proposed to locate the start point of a leaf contour. Experimental results on 440 leaf images from 44 plant species (10 samples from each plant species) show that the fuzzy integral approach can achieve a comparable retrieval performance with the best case of the weighted summation combination. The results also indicate that our approach, which are more efficient, can achieve a better retrieval performance than both the curvature scale space (CSS) method and the modified Fourier descriptor (MFD) method.

关键词： Image retrieval Shape Plants (biology) Histograms Computer vision Humans Fuzzy sets Cascading style sheets Image recognition signal processing

来源：评论

学校读者我要写书评

暂无评论

Video staging in video streaming proxy server

Video staging in video streaming proxy server

引用

IEEE International Conference on multimedia and Expo (ICME)

作者： W.K. Cheuk D.P.K. Lun Center of Multimedia Signal Processing Department of Electronic and Information Engineering Hong Kong University of Science and Technology Hong Kong China

Video staging has been proposed as a mechanism for video streaming proxy servers to better exploit the temporal locality of requests made by clients. It divides a video stream into two parts, i.e. local storage and remote access. It opens a new possibility of scheduling in the video streaming proxy server, with the introduction of disk scheduling on top of network scheduling. However, a simple division cannot put all these resources into good use. We devise a novel video staging algorithm. It considers memory consumption, network bandwidth and disk access requirements so that these resources usage can be optimized accordingly.

关键词： Streaming media Network servers Bandwidth Resource management Smoothing methods Scheduling algorithm Video signal processing signal processing algorithms Large-scale systems Spine

来源：评论

学校读者我要写书评

暂无评论

Novel automatic registration for medical image 5

Novel automatic registration for medical image

引用

5th IFAC Symposium on Modelling and Control in Biomedical Systems 2003

作者： Wang, Xiu Ying Feng, David Dagan Hong, Hai Chi, Zheru Center for Multimedia Signal Processing Department of Electronic and Information Engineering Hong Kong Polytechnic University Hong Kong School of Computer Science Heilongjiang University Harbin150080 China Group School of Information Technologies F09 University of Sydney NSW2006 Australia

As an important integral part of medial image modeling, medical image registration provides unique and necessary information for many clinical applications. In this paper, a novel nonlinear medical image registration approach is proposed. By combining intensity-based registration method with landmark-based registration method, the proposed algorithm can register medical images automatically and accurately. Firstly, the global affine registration method based on image intensity is used to initialize a starting estimation of the robust registration algorithm. Then, by using iterative landmark based algorithm, the affine registration results are registered to further improve the registration accuracy, in which, the novel automatic landmark localization method is introduced and the thin-plate spline is used to refine the registration precision. The clinical MR data are used in our experiments to demonstrate the effectiveness of the proposed algorithm. Copyright © 2003 IF AC.

关键词： Medical applications

来源：评论

学校读者我要写书评

暂无评论

A dot-overlap compensation scheme for Feature-preserving Multiscale Error Diffusion

A dot-overlap compensation scheme for Feature-preserving Mul...

引用

IEEE Region 10 International Conference TENCON

作者： Lai-Yan Wong Yuk-Hee Chan Center of Multimedia Signal Processing Department of Electronic and Information Engineering Hong Kong Polytechnic University Hung Hom Hong Kong China

Feature-preserving Multiscale Error Diffusion (FMED) algorithm is a digital halftoning method to convert a gray scale image into a binary image. This technique is superior to conventional MED methods in a way that it can preserve more image features and provide an output halftone image of good blue noise characteristics. In practice, a printer is not able to produce square ink dots and hence dots may overlap with each other and cover the gird area of neighboring pixels. This dot-overlap effect darkens an image when it is printed. In this paper, a dot compensation scheme is proposed to work with FMED. It compensates for the dot-overlap effect introduced by a printer. Features can be preserved and there is no biasing in the emulated gray scale of the printed image.

关键词： Printers Printing Quantization Ink Diffusion processes Context Simulation

来源：评论

学校读者我要写书评

暂无评论

A robust model generation technique for model-based coding

A robust model generation technique for model-based coding

引用

IEEE International Conference on Image processing

作者： Manson Siu Yuk-Hee Chan Center of Digital Signal Processing for Multimedia Applications Department of Electronic and Information Engineering Hong Kong Polytechnic University Hong Kong China

In conventional model-based coding schemes, predefined static models are generally used. These models cannot adapt to new situations and hence they have to be very specific and cannot be generated from a single generic model even though they are very similar. In this paper, we present a model generation technique that can gradually build a model and dynamically modify it according to new video frames scanned. The proposed technique is robust to the object's orientation in the view and can be efficiently implemented with parallel processing technique. As a result, the proposed technique is more attractive to the practical use of model-based coding techniques in real applications.

关键词： Robustness Graphics Parallel processing Shape Feature extraction Laser modes Data mining Digital signal processing Tracking Video coding

来源：评论

学校读者我要写书评

暂无评论

Content-based scalable H.263 video coding for road traffic monitoring based on regularity of video content

Content-based scalable H.263 video coding for road traffic m...

引用

International Symposium on Intelligent multimedia, Video and Speech processing

作者： W.K.-H. Ho D.P.-K. Lun Center for Multimedia Signal Processing Department of Electronic and Information Engineering Hong Kong Polytechnic University Hung Hom Hong Kong China

ISBN: (纸本)9628576623

For real-time road traffic monitoring, the content-based scalable H.263 video codec was proposed. To achieve a high compression rate, it was suggested to analyze the activity of the target road-traffic video such that moving objects are coded in different data rates according to their speed. However, the analysis performed by that approach relies on the variance of the scene change magnitude. It can be inaccurate when the scene is complicated. An alternative approach is proposed. For the proposed approach, the moving objects, i.e. cars, are first extracted from the steady background. Their activities are then classified as fast or slow by assessing the regularity of their motion. It is achieved by evaluating the zero crossing density of the derivative of the scene change pattern across time. The information is then passed to a modified H.263 encoder to reduce the temporal and spatial redundancies in the video. As compared with the conventional H.263 encoder using for the same application, the proposed system has a 20% increase in compression rate with negligible visual distortion. When comparing with the previous content-based scalable approach, the current approach has a much higher accuracy in activity analysis. The proposed system fully complies with the ITU H.263 standard hence the encoded bit stream is completely comprehensible to the conventional H.263 decoder.

关键词： Video coding Roads Layout Video compression Monitoring Video codecs Analysis of variance Performance analysis Data mining Decoding

来源：评论

学校读者我要写书评

暂无评论

An adaptive model generation technique for model-based video coding

An adaptive model generation technique for model-based video...

引用

IEEE Workshop on multimedia signal processing

作者： M. Siu Yuk-Hee Chan Center of Digital Signal Processing for Multimedia Applications Department of Electronic and Information Engineering Hong Kong Polytechnic University Hong Kong China

关键词： Video coding Graphics Parallel processing Shape Robustness Feature extraction Laser modes Data mining Digital signal processing Tracking

来源：评论

学校读者我要写书评

暂无评论

Methods for improving reliability of GLLS for parametric image generation

Methods for improving reliability of GLLS for parametric ima...

引用

作者： Choi, Hon-Chit Wen, Lingfeng Eberl, Stefan Feng, Dagan Group School of Information Technologies University of Sydney Sydney NSW Australia PET and Nuclear Medicine Dept. Royal Prince Alfred Hospital Sydney NSW Australia Center for Multimedia Signal Processing Department of Electronic and Information Engineering Hong Kong Polytechnic University Hong Kong

ISBN: (纸本)9783902661180

The computationally efficient generalized linear least square (GLLS) algorithm has been successfully applied in positron emission tomography (PET) for constructing parametric images from dynamic data. Recently, we have applied GLLS to substantially more noisy single photon emission computed tomography (SPECT) data. Due to the nature of the data, GLLS sometimes failed to provide physiologically meaningful estimates. In this work, we investigated two potential methods to improve the reliability and success rate of GLLS for estimating kinetic parameters from noisy data:- incorporation of the volume of distribution (Vd) prior into GLLS and applying the bootstrap Monte Carlo method. Our simulation results show that both methods can improve the parameter estimation reliability at the expense of extra computation time. Copyright © 2006 IFAC.

关键词： Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Robust speaker verification from GSM-transcoded speech based on decision fusion and feature transformation

Robust speaker verification from GSM-transcoded speech based...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Man-Wai Mak Ming-Cheung Cheung Sun-Yuan Kung Center for Multimedia Signal Processing Department of Electronic and Information Engineering Hong Kong Polytechnic University China Department of Electrical Engineering Princeton University USA

ISBN: (纸本)0780376633

In speaker verification, a claimant may produce two or more utterances. Typically, the scores of the speech patterns extracted from these utterances are averaged and the resulting mean score is compared with a decision threshold. Rather than simply computing the mean score, we propose to compute the optimal weights for fusing the scores based on the score distribution of the independent utterances and our prior knowledge about the score statistics. More specifically, we use enrollment data to compute the mean scores of client speakers and impostors and consider them to be the prior scores. During verification, we set the fusion weights for individual speech patterns to be a function of the dispersion between the scores of these speech patterns and the prior scores. Experimental results based on the GSM-transcoded speech of 150 speakers from the HTIMIT corpus demonstrate that the proposed fusion algorithm can increase the dispersion between the mean speaker scores and the mean impostor scores. Compared with a baseline approach where equal weights are assigned to all scores, the proposed approach provides a relative error reduction of 19%.

关键词： Robustness Distributed computing Statistical distributions Feature extraction signal processing signal processing algorithms Speech recognition GSM Degradation Aging

来源：评论

学校读者我要写书评

暂无评论

A new efficient block-matching algorithm for motion estimation

引用

Journal of VLSI signal processing Systems for signal, Image, and Video Technology 2006年第1期42卷 21-33页

作者： Mahmoud, Hanan Goel, Sumeer Shaaban, Mohsen Bayoumi, Magdy Faculty of Engineering University of Alexandria University Buildings 9 Albert Street Semouha Alexandria 21321 Egypt Center for Advanced Computer Studies University of Louisiana at Lafayette 110 Rex Street Lafayette LA 70504 Faculty of Engineering University of Alexandria Computer Science Department Department of Computer Engineering Department of Computer Science Center for Advanced Computer Studies University of Louisiana Lafayette Technical Committee on Circuits and Systems for Communication Technical Committee on Signal Processing Design and Implementation Neural Network and the Multimedia Technology Technical Committees University of Louisiana Lafayette

This paper presents a new full-search block-matching algorithm: Multi-stage Interval-based Motion Estimation algorithm (MIME). The proposed algorithm is a block based motion estimation algorithm that utilizes successive elimination technique. We define two approximate functions, as the upper and lower boundaries of the interval that includes the Conventional distortion metric SAD. Each stage in the proposed algorithm;except for the last stage;incorporates low resolution pixels for the boundary functions calculations. The final stage is a full resolution block matching stage. MIME has a high probability of finding the optimal motion vector at any stage of the algorithm. The proposed algorithm reduces the computational complexity by successively eliminating non-candidate blocks from the search window at each stage. This computational reduction leads to enhanced performance in terms of low power consumption and fast motion vector estimation. A low power VLSI implementation of the algorithm is also presented in this paper. Simulation results on benchmark video sequences shows that MIME algorithm eliminates almost 88% of the candidate blocks after only two interval based stages. © Springer Science + Business Media, Inc. 2006.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：